© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 2-MLP-SM
    11. 22922
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal limitations and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/2-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.2.hook_mlp_out
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.18
    1.0%
    313
    +0.15
    0.8%
    23
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    484
    +0.18
    0.03
    23
    +0.15
    0.06
    313
    +0.14
    0.04
    Negative Logits
    arroll
    -1.62
     jurisd
    -1.58
    ño
    -1.57
    iverse
    -1.56
    ashington
    -1.56
    oint
    -1.53
    artments
    -1.52
    "}](#
    -1.51
    icense
    -1.51
    vised
    -1.49
    POSITIVE LOGITS
    ĻĤ
    2.52
     notice
    1.70
    eren
    1.53
     nurse
    1.52
     saying
    1.51
    ¿½
    1.51
    Ĩ
    1.50
     pity
    1.47
    ´
    1.46
     what
    1.43
    Activations Density 2.780%

    No Known Activations